# \#machinevision

**URL:** https://discourse.julialang.org/tag/machinevision/172.md

[Latest](https://discourse.julialang.org/latest.md) · [Categories](https://discourse.julialang.org/categories.md) · [Tags](https://discourse.julialang.org/tags.md)

---

## [Native Julia FID (Fréchet Inception Distance) Computation](https://discourse.julialang.org/t/native-julia-fid-frechet-inception-distance-computation/129798)

<div class="topic-metadata">

**Author:** [@josemanuel22](https://discourse.julialang.org/u/josemanuel22)\
**Replies:** 0\
**Last updated:** [June 11, 2025, 10:00am UTC](https://discourse.julialang.org/t/native-julia-fid-frechet-inception-distance-computation/129798 "2025-06-11T10:00:18Z")

</div>

Is there a relatively simple way to calculate the FID (Fréchet Inception Distance) metric in Julia? Metalhead doesn’t include a pre-trained Inception-v3 model. I know you can try ONNX or PythonCall (though all of those h…

---

## [Julia frameworks for large-scale nonlinear least-squares optimization for computer vision](https://discourse.julialang.org/t/julia-frameworks-for-large-scale-nonlinear-least-squares-optimization-for-computer-vision/49344)

<div class="topic-metadata">

**Author:** [@masoug](https://discourse.julialang.org/u/masoug)\
**Replies:** 3\
**Last updated:** [March 21, 2024, 10:42am UTC](https://discourse.julialang.org/t/julia-frameworks-for-large-scale-nonlinear-least-squares-optimization-for-computer-vision/49344 "2024-03-21T10:42:44Z")

</div>

Hi, Julia newcomer here :slight\_smile: I’m working on learning both Julia and computer vision by implementing common vision algorithms like camera calibration in the Julia language. I’m at a point right now where I’m lo…

---

## [Question: using imdecode in OpenCV.jl](https://discourse.julialang.org/t/question-using-imdecode-in-opencv-jl/111779)

<div class="topic-metadata">

**Author:** [@Dhom\_Bios](https://discourse.julialang.org/u/Dhom_Bios)\
**Replies:** 0\
**Last updated:** [March 18, 2024, 4:18pm UTC](https://discourse.julialang.org/t/question-using-imdecode-in-opencv-jl/111779 "2024-03-18T16:18:48Z")

</div>

Hi everyone! I’m new to Julia and I’m trying to port an opencv script made in python to Julia. Since I haven’t seen an specific subforum dedicated to computer vision, I’m posting this question to general usage. The scr…

---

## [Are you using Julia for visual or 3D geometry optimizations?](https://discourse.julialang.org/t/are-you-using-julia-for-visual-or-3d-geometry-optimizations/104102)

<div class="topic-metadata">

**Author:** [@user664303](https://discourse.julialang.org/u/user664303)\
**Replies:** 2\
**Last updated:** [September 22, 2023, 9:56am UTC](https://discourse.julialang.org/t/are-you-using-julia-for-visual-or-3d-geometry-optimizations/104102 "2023-09-22T09:56:29Z")

</div>

As I’ve mentioned here before, I’m developing a non-linear least squares optimization package similar to the Ceres-solver C++ library. It’s a general NLLS solver, but is particularly well-suited to 3D geometry optimizati…

---

## [\[ANN\] BlobTracking](https://discourse.julialang.org/t/ann-blobtracking/33291)

<div class="topic-metadata">

**Author:** [@baggepinnen](https://discourse.julialang.org/u/baggepinnen)\
**Replies:** 3\
**Last updated:** [June 1, 2023, 8:51pm UTC](https://discourse.julialang.org/t/ann-blobtracking/33291 "2023-06-01T20:51:11Z")

</div>

I was searching around for packages or examples of blob tracking using Julia. To my surprise, I found nothing. Since I needed to do some blob tracking for the purpose of counting birds, I made a small package that can ho…

---

## [\[ANN\] Announcing FastAI.jl](https://discourse.julialang.org/t/ann-announcing-fastai-jl/65394)

<div class="topic-metadata">

**Author:** [@holylorenzo](https://discourse.julialang.org/u/holylorenzo)\
**Replies:** 14\
**Last updated:** [November 29, 2021, 3:50pm UTC](https://discourse.julialang.org/t/ann-announcing-fastai-jl/65394 "2021-11-29T15:50:55Z")

</div>

I am excited to announce the release of FastAI.jl which has been in the works for over a year now. FastAI.jl is a high-level, user-friendly library for training deep learning models built on Flux.jl. It draws inspiration…

---

## [How to convert a JPEG image (from mobile) to a stantard 60k Array{ColorTypes.Gray{FixedPointNumbers.Normed{UInt8, 8}}, 2}) (from Flux.Data.MNIST)?](https://discourse.julialang.org/t/how-to-convert-a-jpeg-image-from-mobile-to-a-stantard-60k-array-colortypes-gray-fixedpointnumbers-normed-uint8-8-2-from-flux-data-mnist/66475)

<div class="topic-metadata">

**Author:** [@sylvaticus](https://discourse.julialang.org/u/sylvaticus)\
**Replies:** 5\
**Last updated:** [August 17, 2021, 10:20am UTC](https://discourse.julialang.org/t/how-to-convert-a-jpeg-image-from-mobile-to-a-stantard-60k-array-colortypes-gray-fixedpointnumbers-normed-uint8-8-2-from-flux-data-mnist/66475 "2021-08-17T10:20:15Z")

</div>

For an exercise I want to let students draw their own digits, scan them with a mobile and let a MINST-trained flux NN to category them. I see that the single MINST images are of type Matrix{ColorTypes.Gray{FixedPointNum…

---

## [\[Julia OpenCV Binding\] no method matching jlopencv\_core\_Mat\_mutable\_data in split function](https://discourse.julialang.org/t/julia-opencv-binding-no-method-matching-jlopencv-core-mat-mutable-data-in-split-function/58284)

<div class="topic-metadata">

**Author:** [@erwanlecarpentier](https://discourse.julialang.org/u/erwanlecarpentier)\
**Replies:** 0\
**Last updated:** [March 31, 2021, 10:25am UTC](https://discourse.julialang.org/t/julia-opencv-binding-no-method-matching-jlopencv-core-mat-mutable-data-in-split-function/58284 "2021-03-31T10:25:55Z")

</div>

Hey! I get an error while using the split function of this Julia OpenCV Binding. Here is the code: using OpenCV m = OpenCV.imread("/absolute/path/to/image.png") OpenCV.split(m) And the error: MethodError: no method …

---

## [Image Super Resolution](https://discourse.julialang.org/t/image-super-resolution/48282)

<div class="topic-metadata">

**Author:** [@kungfooman](https://discourse.julialang.org/u/kungfooman)\
**Replies:** 3\
**Last updated:** [October 15, 2020, 11:32am UTC](https://discourse.julialang.org/t/image-super-resolution/48282 "2020-10-15T11:32:15Z")

</div>

Hi, is there any Julia project focusing on Image Super Resolution? There are lots of these libraries for e.g. Python or Mathematica, but found not one for Julia:

---

## [How to set up convolution layers in Knet.jl vs Flux.jl?](https://discourse.julialang.org/t/how-to-set-up-convolution-layers-in-knet-jl-vs-flux-jl/46983)

<div class="topic-metadata">

**Author:** [@xiaodai](https://discourse.julialang.org/u/xiaodai)\
**Replies:** 1\
**Last updated:** [September 21, 2020, 9:30am UTC](https://discourse.julialang.org/t/how-to-set-up-convolution-layers-in-knet-jl-vs-flux-jl/46983 "2020-09-21T09:30:34Z")

</div>

I have trouble understaind the Knet.jl docs For example conv4(w, x; kwargs...) Execute convolutions or cross-correlations using filters specified with w over tensor x. If w has dimensions (W1,W2,...,Cx,Cy) and x has d…

---

## [Detecting crosses in grids](https://discourse.julialang.org/t/detecting-crosses-in-grids/6720)

<div class="topic-metadata">

**Author:** [@yakir12](https://discourse.julialang.org/u/yakir12)\
**Replies:** 53\
**Last updated:** [August 5, 2020, 9:03pm UTC](https://discourse.julialang.org/t/detecting-crosses-in-grids/6720 "2020-08-05T21:03:49Z")

</div>

Hi all, Thought I’d ask for some image analysis advice: I want to detect the cross points in images of a grid (marked a couple of these in red, just as an example): (a clean and full resolution of this image is avai…

---

## [Fitting a circle/ellipse over an image](https://discourse.julialang.org/t/fitting-a-circle-ellipse-over-an-image/34143)

<div class="topic-metadata">

**Author:** [@razvangheorghe](https://discourse.julialang.org/u/razvangheorghe)\
**Replies:** 15\
**Last updated:** [February 11, 2020, 7:48pm UTC](https://discourse.julialang.org/t/fitting-a-circle-ellipse-over-an-image/34143 "2020-02-11T19:48:03Z")

</div>

Hello, It would be very useful if I could fit a circle/ellipse over a set of density plots. The images are very noisy, but for most of them, you can vaguely make up the shape of an ellipse. Here’s an example: What …

---

## [AkazeFeatures.jl](https://discourse.julialang.org/t/akazefeatures-jl/29563)

<div class="topic-metadata">

**Author:** [@xor0110](https://discourse.julialang.org/u/xor0110)\
**Replies:** 0\
**Last updated:** [October 6, 2019, 7:53pm UTC](https://discourse.julialang.org/t/akazefeatures-jl/29563 "2019-10-06T19:53:00Z")

</div>

AkazeFeatures.jl is a pure Julia port of the original AKAZE image feature extractor. The original code was made in C++, and is available in OpenCV. I have only recently managed to closely reproduce all feature and descr…

---

## [Which autodiff to currently use for a neural network backend?](https://discourse.julialang.org/t/which-autodiff-to-currently-use-for-a-neural-network-backend/15179)

<div class="topic-metadata">

**Author:** [@DoktorMike](https://discourse.julialang.org/u/DoktorMike)\
**Replies:** 10\
**Last updated:** [October 1, 2018, 5:08pm UTC](https://discourse.julialang.org/t/which-autodiff-to-currently-use-for-a-neural-network-backend/15179 "2018-10-01T17:08:14Z")

</div>

Dear community, I’ve been trying out some of the different autodiff packages out there. I’ve run some tests and simulations on the type of problem that I’m addressing. Basically neural networks with high dimensional inp…

---

## [Julia noob trying Computer Vision](https://discourse.julialang.org/t/julia-noob-trying-computer-vision/11679)

<div class="topic-metadata">

**Author:** [@microlifecc](https://discourse.julialang.org/u/microlifecc)\
**Replies:** 6\
**Last updated:** [June 14, 2018, 8:04pm UTC](https://discourse.julialang.org/t/julia-noob-trying-computer-vision/11679 "2018-06-14T20:04:20Z")

</div>

Hi guys! I am new to Julia and am trying to implement some Computer Vision algorithms such as SIFT in Julia. Can you please suggest some resources and packages that might be helpful? Till now I have only gone through the…

---

## [How to transform this grid?](https://discourse.julialang.org/t/how-to-transform-this-grid/6759)

<div class="topic-metadata">

**Author:** [@yakir12](https://discourse.julialang.org/u/yakir12)\
**Replies:** 20\
**Last updated:** [October 31, 2017, 7:04am UTC](https://discourse.julialang.org/t/how-to-transform-this-grid/6759 "2017-10-31T07:04:42Z")

</div>

The following question is partly relevant to camera calibrations, but is relevant to any situation where you want to transform a set of coordinates from one map to another: Say I have a bunch of known coordinates, the…

---

## [Detect corners of different scales](https://discourse.julialang.org/t/detect-corners-of-different-scales/6740)

<div class="topic-metadata">

**Author:** [@yakir12](https://discourse.julialang.org/u/yakir12)\
**Replies:** 0\
**Last updated:** [October 28, 2017, 12:11pm UTC](https://discourse.julialang.org/t/detect-corners-of-different-scales/6740 "2017-10-28T12:11:48Z")

</div>

Are there any settings in Images.imcorner that “tune” the scale or radius of the corners being detected? I tried setting blockSize here but I can’t get it to work… For example, I’d like to detect the corners of the larg…